]> git.proxmox.com Git - mirror_ubuntu-eoan-kernel.git/commit
mm: rework memcg kernel stack accounting
authorRoman Gushchin <guro@fb.com>
Fri, 26 Oct 2018 22:03:19 +0000 (15:03 -0700)
committerLinus Torvalds <torvalds@linux-foundation.org>
Fri, 26 Oct 2018 23:25:19 +0000 (16:25 -0700)
commit9b6f7e163cd0f468d1b9696b785659d3c27c8667
treee92c50c153ad34cfe632761d782ffa872d99f91f
parentc5fd3ca06b4699e251b4a1fb808c2d5124494101
mm: rework memcg kernel stack accounting

If CONFIG_VMAP_STACK is set, kernel stacks are allocated using
__vmalloc_node_range() with __GFP_ACCOUNT.  So kernel stack pages are
charged against corresponding memory cgroups on allocation and uncharged
on releasing them.

The problem is that we do cache kernel stacks in small per-cpu caches and
do reuse them for new tasks, which can belong to different memory cgroups.

Each stack page still holds a reference to the original cgroup, so the
cgroup can't be released until the vmap area is released.

To make this happen we need more than two subsequent exits without forks
in between on the current cpu, which makes it very unlikely to happen.  As
a result, I saw a significant number of dying cgroups (in theory, up to 2
* number_of_cpu + number_of_tasks), which can't be released even by
significant memory pressure.

As a cgroup structure can take a significant amount of memory (first of
all, per-cpu data like memcg statistics), it leads to a noticeable waste
of memory.

Link: http://lkml.kernel.org/r/20180827162621.30187-1-guro@fb.com
Fixes: ac496bf48d97 ("fork: Optimize task creation by caching two thread stacks per CPU if CONFIG_VMAP_STACK=y")
Signed-off-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
include/linux/memcontrol.h
kernel/fork.c